Histopathological Classification Research Articles

The value of the current histological scores and classifications of ANCA glomerulonephritis in predicting long-term outcome

Abstract Background and Aims Three different histological scores- histopathologic classification (Berden), Renal Risk Score (RRS) and the Mayo Clinic Chronicity Score (MCCS) for ANCA associated glomerulonephritis (ANCA-GN) were compared to evaluate their association with patient and kidney prognosis of ANCA-GN. Methods Patients aged > 18 years with at least one year of follow-up and biopsy-proven ANCA-GN entered this retrospective study. Renal biopsies were classified according to Berden's classification, RRS and MCCS. The first endpoint was end-stage kidney disease (ESKD), defined as chronic dialysis or glomerular filtration rate (GFR) <15 ml/min/1.73m2. The second endpoint was ESKD or death. Results Of 152 patients 84 were males, with median age of 63.8 years and followed for 46.9 (IQR 12.8–119) months, 59 (38.8%) reached the first endpoint and 20 died. The Kaplan-Meier curves showed that Berden and RRS were associated with first (Berden: p = 0.004, RRS: p < 0.001) and second endpoint (Berden: p = 0.001, RRS: p < 0.001), MCCS with the first endpoint only when minimal + mild vs moderate + severe groups were compared (p = 0.017) and with the second endpoint (p < 0.001). Among the clinical/histological presentation features, arterial hypertension (OR = 2.75, CI = 1.50–5.06, p = 0.0011), serum creatinine (OR = 1.17, CI = 1.09–1.25, p < 0.0001), and the percentage of normal glomeruli (OR = 0.97, CI = 0.96–0.99, p = 0.009) were the independent predictors of ESKD at multivariate analysis (MA). When the three scores were included in MA, RRS (OR = 2.21, CI = 1.15–4.24, p = 0.017) and MCCS (OR = 2.03, CI = 1.04–3.95, p = 0.037), remained predictive of ESKD but Berden (OR = 1.17, CI = 0.62–2.22, p = 0.691) did not. Conclusion RRS and MCCS scores were independent predictors of kidney survival together with high serum creatinine and arterial hypertension at diagnosis, while Berden classification did not.

Testicular histopathology and follicular stimulating hormone to predict fertility in nonobstructive azoospermia.

To examine the ability of testicular histopathology in Non-obstructive azoospermia (NOA) in predicting sperm retrieval rate (SR), sperm quality and assisted reproductive technology success. A retrospective study recruited clinically diagnosed NOA patients between 2007 and 2015. Testicular biopsy and conventional sperm extraction (TESE) were done concomitantly. Correlation between pathological categories, SR rate, sperm quality and success of intracytoplasmic sperm injection (ICSI) was studied. FSH was measured as a predictor of fertility. One hundred eighteen patients were recruited. Histopathological classification was hypospermatogenesis (HS) 45 (38%), maturation arrest (MA) 22(19%), Sertoli cell only syndrome (SCOS) 34 (29%) and normal spermatogenesis (NS) 17 (14%). FSH value was above normal level in 34 (76%) of HS, 19 (86%) of MA, 32 (94%) of SCOS and 5 (29%) of NS. Positive SR was obtained in 108 (92%) patients. The highest SR rate was seen in NS group 100% and the lowest was in SCOS 26 (77%). The worst sperm quality was found in SCOS as type C represents 46%, followed by MA 40% and HS 24%. Patients had ICSI following TESE had variable success rate as success of ICSI was seen (9/15) for HS, (0/7) for MA, (5/15) for SCOS and (8/9) for NS. FSH is strongly correlated to SR, quality of sperm and success of ICSI as positive SR in normal FSH patients was obtained in 28 (100%) of normal FSH, 70 (97%) of high FSH and 10 (56%) of double high FSH (p value < 001). The success of ICSI significantly correlates with FSH value as normal FSH has 77% success ICSI rate, high FSH (52%) and double high FSH (0%) (p value < 0.001). Testicular biopsy and histopathology findings in NOA are strongly correlated SR rate, quality of sperms, and success of ICSI. FSH is a strong noninvasive predictor of fertility in NOA patients.

Inception-v3 with reduce learning rate for optimization of lung cancer histopathology classification

Inception-v3 with reduce learning rate for optimization of lung cancer histopathology classification

Enhancing Histopathology Breast Cancer Detection and Classification with the Deep Ensemble Graph Network

Enhancing Histopathology Breast Cancer Detection and Classification with the Deep Ensemble Graph Network

Cancer population norms using a new value set for the SF-6Dv2 based on the preferences of patients with breast or colorectal cancer in Quebec.

Because health resources are limited, health programs should be compared to allow the most efficient ones to emerge. To that aim, health utility instruments have been developed to allow the calculation of quality-adjusted life-year (QALY). However, generic instruments, which can be used by any individual regardless of their health profile, typically consider the preferences of the general population when developing their value set. Consequently, they are often criticized for lacking sensitivity in certain domains, such as cancer. In response, the latest version of the Short Form 6-Dimension (SF-6Dv2) has been adapted to suit the preferences of patients with breast or colorectal cancer in the Canadian province of Quebec. By extension, our study's aim was to determine cancer population norms of utility among patients with breast or colorectal cancer in Quebec using the SF-6Dv2. To determine the cancer population norms, we exploited the data that were used in the development of a new value set for the SF-6Dv2. This value set was developed considering the preferences of patients with breast or colorectal cancer. Stratification by time of data collection (i.e., T1 and T2), sociodemographic variables (i.e., age, sex, body mass index, and self-reported health problems affecting quality of life), and clinical aspects (i.e., cancer site, histopathological classification, cancer stage at diagnosis, modality, and treatment characteristics) was performed. In 353 observations, patients were more likely to have negative utility scores at T1 than at T2. Males had higher mean utility scores than females considering type of cancer and comorbidities. Considering the SF-6Dv2's dimensions, more females than males reported having health issues, most which concerned physical functioning. Significant differences by sex surfaced for all dimensions except "Role Limitation" and "Mental health." Patients with multifocal cancer had the highest mean and median utility values in all cancer sites considered. Cancer population norms can serve as a baseline for interpreting the scores obtained by a given population in comparison to the situation of another group. In this way, our results can assist in comparing utility scores among cancer patients with different sociodemographic groups to other patients/populations groups. To our knowledge, our identified utility norms are the first for patients with breast or colorectal cancer from Quebec.

Evaluation of the prognostic potential of histopathological subtyping in high-grade serous ovarian carcinoma.

High-grade serous ovarian carcinoma (HGSOC) can be categorized into four gene expression-based subtypes, with supposedly distinct prognoses and treatment responses. Murakami et al. translated these gene expression-based subtypes into the histopathological mesenchymal, immunoreactive, solid and proliferative, and papilloglandular subtypes, showing differences in survival outcomes. Miyagawa et al. refined these criteria to improve the interobserver concordance. The current retrospective study evaluated the interobserver variability and the prognostic differences between the histopathologic subtypes using the criteria of both Murakami et al. and Miyagawa et al. in 208 HGSOC cases. The mesenchymal subtype was considered first, followed by the immunoreactive subtype. Non-conforming cases were categorized as solid and proliferative or papilloglandular. The mesenchymal subtype was identified in 122 patients (58.7%) for both criteria. Using the criteria of Murakami et al., 10 cases (4.8%) were immunoreactive, 26 (12.5%) solid and proliferative, and 50 (24%) papilloglandular, with a concordance rate of 62.5% (κ = 0.34, p < .001). Using the Miyagawa et al. criteria, 23 cases (11%) were immunoreactive, 20 (9.6%) solid and proliferative, and 43 (20.7%) papilloglandular. No survival differences were observed between the subtypes. The fair reproducibility of the histopathological subtype classification of HGSOC and the lack of survival differences among these subtypes indicate the need for further refinement of the criteria and exploration of their correlation with overall survival outcomes before clinical application.

Histological interpretation of spitzoid tumours: an extensive machine learning-based concordance analysis for improving decision making.

The histopathological classification of melanocytic tumours with spitzoid features remains a challenging task. We confront the complexities involved in the histological classification of these tumours by proposing machine learning (ML) algorithms that objectively categorise the most relevant features in order of importance. The data set comprises 122 tumours (39 benign, 44 atypical and 39 malignant) from four different countries. BRAF and NRAS mutation status was evaluated in 51. Analysis of variance score was performed to rank 22 clinicopathological variables. The Gaussian naive Bayes algorithm achieved in distinguishing Spitz naevus from malignant spitzoid tumours with an accuracy of 0.95 and kappa score of 0.87, utilising the 12 most important variables. For benign versus non-benign Spitz tumours, the test reached a kappa score of 0.88 using the 13 highest-scored features. Furthermore, for the atypical Spitz tumours (AST) versus Spitz melanoma comparison, the logistic regression algorithm achieved a kappa value of 0.66 and an accuracy rate of 0.85. When the three categories were compared most AST were classified as melanoma, because of the similarities on histological features between the two groups. Our results show promise in supporting the histological classification of these tumours in clinical practice, and provide valuable insight into the use of ML to improve the accuracy and objectivity of this process while minimising interobserver variability. These proposed algorithms represent a potential solution to the lack of a clear threshold for the Spitz/spitzoid tumour classification, and its high accuracy supports its usefulness as a helpful tool to improve diagnostic decision-making.

Focused active learning for histopathological image classification

Active Learning (AL) has the potential to solve a major problem of digital pathology: the efficient acquisition of labeled data for machine learning algorithms. However, existing AL methods often struggle in realistic settings with artifacts, ambiguities, and class imbalances, as commonly seen in the medical field. The lack of precise uncertainty estimations leads to the acquisition of images with a low informative value. To address these challenges, we propose Focused Active Learning (FocAL), which combines a Bayesian Neural Network with Out-of-Distribution detection to estimate different uncertainties for the acquisition function. Specifically, the weighted epistemic uncertainty accounts for the class imbalance, aleatoric uncertainty for ambiguous images, and an OoD score for artifacts. We perform extensive experiments to validate our method on MNIST and the real-world Panda dataset for the classification of prostate cancer. The results confirm that other AL methods are ‘distracted’ by ambiguities and artifacts which harm the performance. FocAL effectively focuses on the most informative images, avoiding ambiguities and artifacts during acquisition. For both experiments, FocAL outperforms existing AL approaches, reaching a Cohen’s kappa of 0.764 with only 0.69% of the labeled Panda data.

Uncertainty-Guided Asymmetric Consistency Domain Adaptation for Histopathological Image Classification

Deep learning has achieved remarkable progress in medical image analysis, but its effectiveness heavily relies on large-scale and well-annotated datasets. However, assembling a large-scale dataset of annotated histopathological images is challenging due to their unique characteristics, including various image sizes, multiple cancer types, and staining variations. Moreover, strict data privacy in medicine severely restricts data sharing and poses significant challenges in acquiring large-scale and well-annotated histopathological images. To tackle these constraints, Transfer Learning (TL) provides a promising solution by exploiting knowledge from another domain. This study proposes the Uncertainty-guided asymmetric Consistency Domain Adaptation (UCDA), which does not require accessing the source data and is composed of two essential components, e.g., Uncertainty-guided Source-free Transfer Learning (USTL) and Asymmetric Consistency Learning (ACL). In detail, USTL facilitates a secure mapping of the source domain model’s feature space onto the target domain, eliminating the dependency on source domain data to protect data privacy. At the same time, the ACL module measures the symmetry and asymmetry between the source and target domains, bridging the information gap and preserving inter-domain differences among medical images. We comprehensively evaluate the effectiveness of UCDA on three widely recognized and publicly available datasets, namely NCTCRC-HE-100K, PCam, and LC25000. Impressively, our proposed method achieves remarkable performance on accuracy and F1-scores. Additionally, feature visualizations effectively demonstrate the exceptional generalizability and discriminative power of the learned representations. These compelling results underscore the significant potential of UCDA in driving the advancement of deep learning techniques within the realm of histopathological image analysis.

Functional Classification of Fusion Proteins in Sarcoma.

Sarcomas comprise a heterogeneous group of malignant tumors of mesenchymal origin. More than 80 entities are associated with different mesenchymal lineages. Sarcomas with fibroblastic, muscle, bone, vascular, adipocytic, and other characteristics are distinguished. Nearly half of all entities contain specific chromosomal translocations that give rise to fusion proteins. These are mostly pathognomonic, and their detection by various molecular techniques supports histopathologic classification. Moreover, the fusion proteins act as oncogenic drivers, and their blockade represents a promising therapeutic approach. This review summarizes the current knowledge on fusion proteins in sarcoma. We categorize the different fusion proteins into functional classes, including kinases, epigenetic regulators, and transcription factors, and describe their mechanisms of action. Interestingly, while fusion proteins acting as transcription factors are found in all mesenchymal lineages, the others have a more restricted pattern. Most kinase-driven sarcomas belong to the fibroblastic/myofibroblastic lineage. Fusion proteins with an epigenetic function are mainly associated with sarcomas of unclear differentiation, suggesting that epigenetic dysregulation leads to a major change in cell identity. Comparison of mechanisms of action reveals recurrent functional modes, including antagonism of Polycomb activity by fusion proteins with epigenetic activity and recruitment of histone acetyltransferases by fusion transcription factors of the myogenic lineage. Finally, based on their biology, we describe potential approaches to block the activity of fusion proteins for therapeutic intervention. Overall, our work highlights differences as well as similarities in the biology of fusion proteins from different sarcomas and provides the basis for a functional classification.

Typical metastases, atypical course of the disease and morphology

The process of tumor differentiation is a central aspect of the histopathological classification of solid malignancies and is closely related to the biological behavior of the tumor (poorly differentiated tumors/dedifferentiated tumors are known to be more aggressive than more differentiated tumors). The mechanisms by which tumor cell differentiation is disrupted are poorly understood, but pathologists and molecular tumor biologists have introduced the concept of dedifferentiation to explain the phenotypic changes that occur in solid tumors. In this review, we discuss a case of detection of dedifferentiated cancer, where even with the help of molecular testing of a tumor sample, we were not completely able to unambiguously determine the original source of the process, which entailed difficulties in choosing treatment tactics. And the main question that we asked ourselves during the treatment process: should treatment be based on molecular markers identified in the tumor, or should treatment be carried out according to the recommendations for the treatment of tumors of an undetected primary location with empirically selected chemotherapy?

Memory-Efficient Prompt Tuning for Incremental Histopathology Classification

Recent studies have made remarkable progress in histopathology classification. Based on current successes, contemporary works proposed to further upgrade the model towards a more generalizable and robust direction through incrementally learning from the sequentially delivered domains. Unlike previous parameter isolation based approaches that usually demand massive computation resources during model updating, we present a memory-efficient prompt tuning framework to cultivate model generalization potential in economical memory cost. For each incoming domain, we reuse the existing parameters of the initial classification model and attach lightweight trainable prompts into it for customized tuning. Considering the domain heterogeneity, we perform decoupled prompt tuning, where we adopt a domain-specific prompt for each domain to independently investigate its distinctive characteristics, and one domain-invariant prompt shared across all domains to continually explore the common content embedding throughout time. All domain-specific prompts will be appended to the prompt bank and isolated from further changes to prevent forgetting the distinctive features of early-seen domains. While the domain-invariant prompt will be passed on and iteratively evolve by style-augmented prompt refining to improve model generalization capability over time. In specific, we construct a graph with existing prompts and build a style-augmented graph attention network to guide the domain-invariant prompt exploring the overlapped latent embedding among all delivered domains for more domain-generic representations. We have extensively evaluated our framework with two histopathology tasks, i.e., breast cancer metastasis classification and epithelium-stroma tissue classification, where our approach yielded superior performance and memory efficiency over the competing methods.

A deep multi-branch attention model for histopathological breast cancer image classification

AbstractSince the impressive superior performance demonstrated by deep learning methods is widely used in histopathological image analysis and diagnosis, existing work cannot fully extract the information in the breast cancer images due to the limited high resolution of histopathological images. In this study, we construct a novel intermediate layer structure that fully extracts feature information and name it DMBANet, which can extract as much feature information as possible from the input image by up-dimensioning the intermediate convolutional layers to improve the performance of the network. Furthermore, we employ the depth-separable convolution method on the Spindle Structure by decoupling the intermediate convolutional layers and convolving them separately, to significantly reduce the number of parameters and computation of the Spindle Structure and improve the overall network operation speed. We also design the Spindle Structure as a multi-branch model and add different attention mechanisms to different branches. Spindle Structure can effectively improve the performance of the network, the branches with added attention can extract richer and more focused feature information, and the branch with residual connections can minimize the degradation phenomenon in our network and speed up network optimization. The comprehensive experiment shows the superior performance of DMBANet compared to the state-of-the-art method, achieving about 98% classification accuracy, which is better than existing methods. The code is available at https://github.com/Nagi-Dr/DMBANet-main.

Abstract 5057: microRNA profiling in combination with whole exome sequencing reveals insights into long-term recurrence patterns in chordoma

Abstract While few studies on miRNA profiling in primary chordomas have been published, there is no data on the miRNA landscape of long-term recurrences. Therefore, we performed a miRNA analysis and whole exome sequencing (WES) investigating four patients with multiple recurrences over seven to 16 years and eight patients with non-recurrent tumors (NRTs), conventional, sacral chordomas in order to compare both groups as well as the recurrence cases (RCs) to each other. Our aim was to find typical miRNA patterns distinguishing the recurrences from the NRTs. After histopathological classification, immunohistochemical and morphometric analysis, DNA and miRNA were extracted from formalin-fixed-paraffin-embedded tissue samples and analyzed by WES and Nanostring. The microRNA regulation patterns showed similarities within RCs differing from NRTs. In unsupervised clustering there is a tendency of recurrences clustering apart from the NRTs. The differential expression between cases developing recurrences and NRTs showed highly significant differences between both groups with 32 miRNAs upregulated in the RCs being downregulated in NRTs. The miRNA expression of long-term recurrences of each patient are quite homogenous differing only from their primary tumor. Comparing NRTs with primary tumors that would later develop long-term recurrences showed significant up-regulation of 5 miRNAs in the RCs. This suggests a pivotal molecular difference between singular and long-term recurring chordomas. Our WES analysis confirmed known and revealed possible new driver genes. Recurring tumors had a higher number of mutations classified as pathogenic as well as increased proliferation rates and pleomorphic changes. Recurrences displayed a change in mutational distribution, showing considerably more disturbances in embryonic signaling and our proposed driver genes. Intriguingly, our study found a progress in number of alterations throughout the recurrences most of all affecting chromatin regulation and the new drivers. Less disruption of these pathways in primary cases than in recurrences implies their pivotal role not only in chordoma formation, but also in recurrence evolution. The miRNA alterations were correlated with the genomic differences. Validated affected genes of miRNAs deregulated primarily in the recurrences are involved in those pathways as well. As current targeted therapy options are only sporadically altered in few patients, the progress in number of pathogenic mutations throughout the recurrences as well as the drastic change in miRNA expression could present new research approaches for chordomas with long-term recurrences. Combined clinical and molecular studies of miRNA patterns and genetic alterations could expand the understanding of recurrence development leading to new therapeutic targets inhibiting or delaying recurrence formation. Citation Format: Sarah R. Ullmann, Franziska Karras, Julian Schreier, Kerstin Körber-Ferl, David A. Ullmann, Sabine Franke, Albert Roessner, Dörthe Jechorek. microRNA profiling in combination with whole exome sequencing reveals insights into long-term recurrence patterns in chordoma [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 5057.

Abstract 338: Unraveling layers of proteogenomic complexity in cancer through multiomic exploration of archived FFPE tissue

Abstract Formalin Fixed Paraffin Embedded (FFPE) tissues are a staple in clinical diagnostics associated with solid tumor. The preserved tumor tissue can be interrogated using classical histopathology and complemented with molecular approaches to elucidate cancerous SNPs, indels, structural variants, repeat expansion, copy number expansions, and mutational burden. Increasingly, approaches are being deployed to interrogate tissue not only through individual datasets but through integrated approaches that provide spatial information that defines the tumor microenvironment. Here, we illustrate using FFPE blocks from various tissues a multiomic workflow that allows for deep exploration of the molecular underpinnings of cancerous tissue. FFPE blocks were serially sliced into various FFPE slides with a single slide H&amp;E stained. Individual slides were then utilized to explore the genome, epigenome, single cell RNA-seq, and digital spatial profiling. Genome information was captured using hybrid capture based approaches (whole exome sequencing and targeted cancer panel) followed by deep NGS on an Illumina platform and analyzed for a variety of variants and tumor mutational burden. DNA methylation was detailed using target capture probes targeting DNA methylation sites. Single cell approaches were applied to explore the transcriptome using 10X Genomics scRNAseq Flex kit. Digital spatial profiling was done using the NanoString for both transcriptomics and proteomics, with the GeoMx Whole Transcriptome Atlas and Human Core and Pan-Tumor protein panels. Aggregating these data illustrates the expanding landscape of information that can be extracted from FFPE derived tissue and the potential for novel discovery and diagnostic power integrating these complex data types holds. Citation Format: Andrea J. O'Hara, Yang Han, Ilaria DeVito, Laure Turner, Haythem Latif. Unraveling layers of proteogenomic complexity in cancer through multiomic exploration of archived FFPE tissue [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 338.

Abstract 2942: Deciphering histological subtype-associated cellular and molecular characteristics of lung adenocarcinoma using single-cell RNA sequencing and spatial transcriptomics

Abstract Lung adenocarcinoma (LUAD) is the most frequently observed subtype found in non-small cell lung cancer (NSCLC). Despite its high prevalence, the molecular and histological heterogeneity in LUAD pose a significant challenge for providing effective patient care and aiming to reduce the high mortality rate. The histopathological classification proposed by WHO in 2015 describes five histologic patterns of lung adenocarcinoma (lepidic, acinar, papillary, micropapillary, and solid), and it has been shown that the existence of high-grade subtypes (micropapillary and solid) is associated with poorer survival outcomes. Nevertheless, the specific cellular and molecular mechanisms responsible for these clinical outcome differences based on distinct histological patterns remain unclear. Here, we conducted single-cell RNA sequencing (scRNA-seq) to unveil insights into the tumor microenvironment (TME) and identify cancer cell biomarkers associated with distinct histological patterns. Our study involved 18 specimens from primary LUAD patients who underwent surgical resection, all of whom were previously untreated. These specimens were classified into three groups: acinar/papillary (A/P), micropapillary (MP), and solid. Remarkably, patients with solid-type tumors showed a notable enrichment of CD8+ T cell exhaustion, alongside a significant abundance of GPNMB-high macrophages in the myeloid compartment. Additionally, macrophages from the solid-type demonstrated cholesterol-efflux activation, particularly in alveolar macrophages. It is well-known that cholesterol efflux-activated macrophages display a tumor-associated macrophage phenotype, contributing to immunosuppression in the TME. In contrast, the A/P group exhibited a higher enrichment of mast cells compared to the solid-type. This suggests that the solid-type tumor landscape is more immunosuppressive than the A/P group. In the context of cancer cells, we identified that A/P cancer cells displayed a well-differentiated pattern with a high alveolar epithelial type II cell (AT2) signature. In contrast, solid-type cancer cells showed poorly differentiated states, coupled with a significant activation of the epithelial-mesenchymal transition (EMT) process. Remarkably, even within A/P patients, those with a small portion of solid patterns in the tumor tissue showed higher clonal complexity compared to patients without any solid pattern. Furthermore, we found that cancer cell plasticity can be regulated by cell-cell interactions in the TME. Collectively, this study unveils the relationship between histological patterns and the TME, encompassing distinct immune responses and molecular characteristics of cancer cells in LUAD. These findings provide valuable insights for potential targeted therapeutic strategies. Citation Format: Ju Sung Lee, Ji Yun Jeong, Mi Jeong Hong, Hyo-Gyoung Kang, Jin Eun Choi, Ju Young Kim, Yoon Ha Choi, Jong Kyoung Kim, Shin Yup Lee. Deciphering histological subtype-associated cellular and molecular characteristics of lung adenocarcinoma using single-cell RNA sequencing and spatial transcriptomics [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 2942.

Retracted: Detection of Breast Cancer Using Histopathological Image Classification Dataset with Deep Learning Techniques.

[This retracts the article DOI: 10.1155/2022/8363850.].

Lack of clinical utility of serum macrophage migration inhibitory factor (MIF) for monitoring therapy response and estimating prognosis in advanced lung cancer.

Lung cancer is a major burden to global health and is still among the most frequent and most lethal malignant diseases. Macrophage migration inhibitory factor (MIF) is a proinflammatory cytokine involved in a variety of processes including tumorigenesis, formation of a tumor microenvironment and metastasis. It is therefore a potential prognostic biomarker in malignant diseases. In this study, we investigated the applicability of MIF in serum samples as a biomarker in lung cancer. In a retrospective approach, we analyzed the sera of 79 patients with non-small-cell lung cancer (NSCLC) and 14 patients with small-cell lung cancer (SCLC) before the start of chemotherapy, as well as before the second and third chemotherapy cycle, respectively. Serum MIF levels were measured using a sandwich immunoassay with a sulfo-tag-labelled detection antibody, while pro-gastrin releasing peptide (proGRP) levels were determined with an enzyme-linked immunosorbent assay. No difference in serum MIF levels between responders and non-responders to chemotherapy was observed at all time points, while proGRP levels were significantly lower in responders before the second chemotherapy cycle (p = 0.012). No differences in biomarker levels depending on the histopathological classification of NSCLC patients was found. Moreover, in ROC curve analyses MIF was not able to distinguish between responders and non-responders to therapy. proGRP could differentiate between responders and non-responders before the second chemotherapy cycle (p = 0.015) with sensitivities of 43% at 90% and 95% specificity, respectively. Likewise, proGRP yielded significantly longer survival times of patients with low proGRP concentrations before the second chemotherapy cycle (p = 0.015) in Kaplan-Meier analyses, yet MIF showed no significant differences in survival times at all time points. Comparison with the biomarkers CEA and CYFRA 21-1 in the same cohort showed that these established biomarkers clearly performed superior to MIF and proGRP. From the present results, there is no indication that serum MIF may serve as a biomarker in prognosis and monitoring of response to therapy in lung cancer. Limitations of this study include its retrospective design, the inclusion of a larger NSCLC and a smaller SCLC subgroup, the classical chemotherapeutic treatment, the use of a non-diagnostic immunoassay (RUO-test) for MIF measurement and the lack of a validation cohort. Strengths of the study are its highly standardized procedures concerning sample collection, preanalytic treatment, measurements and quality control of the laboratory assays.

Emerging Advances in Endometrial Cancer: Integration of Molecular Classification into Staging for Enhanced Prognostic Accuracy and Implications for Racial Disparities.

Since the 2009 FIGO staging update, focused exclusively on the anatomic extent of disease, there have been several advances in the understanding of the pathologic and molecular features of endometrial cancer. In a significant departure from the 2009 FIGO staging system, the 2023 FIGO staging update integrates both histopathological and molecular classification. With the inclusion of non-anatomic pathologic parameters such as histology, tumor grade, lymphovascular space invasion, and molecular subtype, the 2023 FIGO staging update aims to create more clinically relevant substages that improve prognostic value and allows for more individualized treatment paradigms. This review will evaluate the clinical impact of the 2023 FIGO staging update, describe the stage shifts that lead to higher prognostic precision, and illustrate the current state of molecular analysis in clinical practice. Furthermore, this review will explore how incorporating factors such as molecular subtype into endometrial cancer staging can offer valuable insights into the racial disparities seen in morbidity and mortality.

Epidemiology and classification for canine and feline mammary gland tumors: a histopathological survey of 437 mammary gland tumor biopsies performed in a secondary care hospital in Chiang Mai, Thailand from 2012 to 2019.

Metastatic disease resulting from mammary gland tumors (MGTs) is a known cause of death among dogs and cats. Keys to successful prevention and management strategies involve the accurate recording of diagnostic data. This retrospective study reviewed the epidemiology and classification of canine mammary gland tumors (CMTs) and feline mammary gland tumors (FMTs), as well as the factors including sex, age, and breed related to the occurrence of these tumors. Accordingly, 1,736 tumor biopsy cases were reported from 2012 to 2019 at Chiang Mai University Small Animal Hospital, Thailand, with 1,639 canine tumor biopsy cases and 97 feline tumor biopsy cases. The proportion of CMTs was reported at 24.5% (401/1,639) for all canine tumor biopsy cases. Benign and malignant tumors were reported at 14.5% (58/401) and 85.5% (343/401) for all CMT cases, respectively. The mean age of dogs affected by benign CMTs was 9.0±3.0 years, which was significantly lower than for malignant CMTs at 9.9±2.8 years (P=0.0239). According to histopathological classification, benign mixed tumors and simple carcinoma types were highest among benign and malignant CMT cases, respectively. Moreover, female dogs were at significantly higher risk of developing mammary gland tumors (OR = 45.8, 95% CI [3.9-86.0], P<0.0001) than male dogs, as well as older dogs (>8 years) (OR = 1.7, 95% CI [1.2-2.2], P=0.0001) compared to young ones (≤8 years). The proportion of FMTs was 37.1% (36/97) for all feline tumor biopsy cases. Benign and malignant tumors for all FMTs were reported at 16.7% (6/36) and 83.3% (30/36), respectively. According to histopathological classifications, adenoma and simple carcinoma were present in the highest proportion among benign and malignant FMTs, respectively. Female cats were at a significantly higher risk of developing mammary gland tumors than male cats (OR=25.7, 95% CI [3.9-272.8], P<0.0001). There was a high proportion of MGT cases compared with other tumor cases reported in a secondary care hospital in Chiang Mai, Thailand from 2012 to 2019, and malignant tumor biopsies have been more frequently observed than benign tumor biopsies in both CMT and FMT cases. The resulting data originating from this study can be an aid for veterinary oncologists in better educating clients and planning treatment and prevention strategies and it can be used as a basis for further experimental studies in the oncology section.